Skip to main content
AITier

Qwen3.5 397B A17B (Non-reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

Description

Qwen3.5-397B-A17B is Qwen's flagship Mixture-of-Experts model with 397 billion total parameters and 17 billion activated parameters. It delivers state-of-the-art performance across knowledge, reasoning, coding, mathematics, multilingual understanding, instruction following, long context, and agent tasks.

Release Date
2026-02-16
Parameters
397.0B
Context Length
262K
Modalities
audio, image, text, video

Capability Radar

29
general
41
coding
86
reasoning
57
scienceest.
60
agents
70
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agentic Capability60
55.0
LS
Code Ranking100
67.0
AA
General Ranking110
62.0
AA
Reasoning69
58.0
LS
Science80
64.0
AA

Benchmark Scores (LLM Stats)

Agents

GDPval-AA961.00 / 3000SR
t2-bench86.7%SR
WideSearch74.0%SR
BFCL-V472.9%SR
BrowseComp69.0%SR
Terminal-Bench 2.052.5%SR
VITA-Bench49.7%SR
MCP-Mark46.1%SR
Toolathlon38.3%SR
DeepPlanning34.3%SR

Biology

GPQA88.4%SR

Chemistry

SuperGPQA70.4%SR

Code

SWE-Bench Verified76.4%SR
SWE-bench Multilingual69.3%SR

Coding

SecCodeBench68.3%SR

Communication

Multi-Challenge67.6%SR

Finance

MMLU-Pro87.8%SR
MMLU-ProX84.7%SR

General

MMLU-Redux94.9%SR
C-Eval93.0%SR
IFEval92.6%SR
Global PIQA89.8%SR
MMMLU88.5%SR
MAXIFE88.2%SR
Include85.6%SR
LiveCodeBench v683.6%SR
IFBench76.5%SR
LongBench v263.2%SR
NOVA-6359.1%SR

Language

WMT24++78.9%SR

Long Context

AA-LCR68.7%SR

Math

HMMT 202594.8%SR
HMMT2592.7%SR
AIME 202691.3%SR
IMO-AnswerBench80.9%SR
PolyMATH73.3%SR
Humanity's Last Exam28.7%SR

Reasoning

BrowseComp-zh70.3%SR
Seal-046.9%SR

AA Evaluation Indices

Intelligence Index
32.0
Gpqa
0.9
Tau2
0.8
Lcr
0.6
Ifbench
0.5
Scicode
0.4
Terminalbench Hard
0.4
Hle
0.2

LLM Stats Category Scores

Legal
100
Finance
100
Agents
97
General
61
Reasoning
35
Language
90
Biology
90
Instruction Following
80
Math
80
Physics
80
Structured Output
80
Frontend Development
80
Healthcare
80
Chemistry
80
Long Context
70
Multimodal
70
Search
70
Spatial Reasoning
70
Code
70
Communication
70
Economics
70
Tool Calling
60
Vision
50

Pricing

Input Price$0.6 / 1M tokens
Output Price$3.6 / 1M tokens
Blended Price (3:1)$1.35 / 1M tokens

Speed

Tokens/sec52.9
Time to First Token1.75s
Time to Answer1.75s

Provider Price Ranking

Provider Price Ranking

9 providers

Cheapest: NovitaMost Expensive: OVHcloud AI Endpoints
ProviderInputOutput
1NovitaCheapest
$0
$0
2CrofAI
$0.35
$1.75
3Alibaba (China)
$0.43
$2.58
4DigitalOcean
$0.55
$3.5
5AlibabaPRIMARY
$0.6
$3.6
6Scaleway
$0.6
$3.6
7NanoGPT
$0.6
$3.6
8Cortecs
$0.6
$3.6
9OVHcloud AI Endpoints
$0.71
$4.25

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis